IP Library › Granted Patent US 12,309,027
Granted Patent B2
US 12,309,027 · App. 17/995,747 · Granted May 20, 2025

Coordination and control mechanism for conflict resolution for network automation functions

Inventors: Anubhab Banerjee (Munich, DE); Stephen S. Mwanje (Dorfen, DE)
Assignee: NOKIA TECHNOLOGIES OY
H04L41/0823H04L41/0873
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,309,027
App. No.
17/995,747
Granted
May 20, 2025
Kind
B2
Abstract

An apparatus and a method are provided, by which a controller receives configuration sets from at least two network automation functions, each network automation function determining the configuration set such that it is optimal for achieving an objective of the network automation function. The controller determines an optimal network configuration based on the configuration sets received from the at least two network automation functions.

Claims (47)

1. An apparatus, comprising:

at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to perform:

receiving configuration sets from at least two network automation functions, each network automation function determining an associated configuration set that is optimal for achieving an objective of the network automation function, and

determining an optimal network configuration based on the associated configuration set received from the at least two network automation functions,

wherein an optimal network configuration is a network configuration achieving the best performance target for a network metric, or a network configuration achieving a performance target for a network metric, which is higher than a certain threshold, wherein an optimal network configuration is a network configuration which achieves a maximum quality of service (QOS) for users of the network and is higher than a certain threshold,

wherein the apparatus further comprises a pre-action controller for network automation functions that determines an optimal network configuration by resolving existing configuration conflicts among the network automation functions,

wherein the pre-action controller determines the optimal configuration for the network beforehand, so that the users of the network get maximum QoS when the selected optimal configuration is applied,

wherein the pre-action controller is a separate function from the network automation functions, one layer above the network automation functions in operational hierarchy,

wherein during the process of determining the optimal configuration, if there occurs any conflict between two or multiple network automation functions over a particular parameter or interest, the pre-action controller resolves the conflict instantaneously,

wherein the pre-action controller receives configuration sets from all conflicting network automation functions as inputs with each network automation function providing the controller with the configuration set that is most favorable for the network automation function's objectives and which is expected to deliver the most utility according to the network automation function's objective,

wherein the pre-action controller receives from the conflicting network automation functions as inputs utility functions that map each configuration value to the utility the network automation functions achieve using that value,

wherein based on all the inputs, the pre-action controller determines an optimal system configuration using Nash's social welfare function to resolve conflicts and to compute the optimal network configuration,

wherein the output of the pre-action controller, the optimal network configuration, is used to reconfigure either the network automation functions for the network,

wherein the pre-action controller reconfigures the network automation functions so that they now use the optimal network configuration for any future network control actions, or the pre-action controller may directly configure the network with the optimal network configuration.

2. The apparatus according to claim 1 , wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to further perform:

determining that a conflict is present among the at least two network automation functions by determining that the configuration sets of the at least two network automation functions do not match with each other, and that utility functions received from the at least two network automation functions do not match with each other, the utility functions describing the input-output relationship of the network automation functions, respectively;

determining the optimal network configuration by solving the conflict among the at least two network automation functions.

3. The apparatus according to claim 2 , wherein each configuration set comprises a range for a parameter having a minimum value and a maximum value, the parameters being not the same for the configuration sets of the at least two network automation functions, and the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to further perform:

determining that a conflict is present by determining that the minimum values and the maximum values of ranges for the parameter of the configuration sets of the at least two network automation functions do not match with each other.

4. The apparatus according to claim 1 , wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to further perform:

determining the optimal network configuration also based on a plurality of utility functions applied by the at least two network automation functions.

5. The apparatus according to claim 1 , wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to further perform:

receiving a request from at least one network automation function to re-determine the optimal network configuration, the request comprising a modified configuration set, and

sending, in response to receiving the modified configuration set, a request to at least one other network automation function to provide configuration sets.

6. A method, comprising:

receiving configuration sets from at least two network automation functions, each network automation function determining an associated configuration set such that is optimal for achieving an objective of the network automation function, and

determining an optimal network configuration based on the associated configuration set received from the at least two network automation functions,

wherein an optimal network configuration is a network configuration achieving the best performance target for a network metric, or a network configuration achieving a performance target for a network metric, which is higher than a certain threshold, wherein an optimal network configuration is a network configuration which achieves a maximum quality of service (QOS) for users of the network and is higher than a certain threshold,

wherein a pre-action controller for network automation functions determines an optimal network configuration by resolving existing configuration conflicts among the network automation functions,

wherein the pre-action controller determines the optimal configuration for the network beforehand, so that the users of the network get maximum QoS when the selected optimal configuration is applied,

wherein the pre-action controller is a separate function from the network automation functions, one layer above the network automation functions in operational hierarchy,

wherein during the process of determining the optimal configuration, if there occurs any conflict between two or multiple network automation functions over a particular parameter or interest, the pre-action controller resolves the conflict instantaneously,

wherein the pre-action controller receives configuration sets from all conflicting network automation functions as inputs with each network automation function providing the controller with the configuration set that is most favorable for the network automation function's objectives and which is expected to deliver the most utility according to the network automation function's objective,

wherein the pre-action controller receives from the conflicting network automation functions as inputs utility functions that map each configuration value to the utility the network automation functions achieve using that value,

wherein based on all the inputs, the pre-action controller determines an optimal system configuration using Nash's social welfare function to resolve conflicts and to compute the optimal network configuration,

wherein the output of the pre-action controller, the optimal network configuration, is used to reconfigure either the network automation functions for the network,

wherein the pre-action controller reconfigures the network automation functions so that they now use the optimal network configuration for any future network control actions, or the pre-action controller may directly configure the network with the optimal network configuration.

7. The method to claim 6 , further comprising:

determining that a conflict is present among the at least two network automation functions by determining that the configuration sets of the at least two network automation functions do not match with each other, and that utility functions received from the at least two network automation functions do not match with each other, the utility functions describing the input-output relationship of the network automation functions, respectively;

determining the optimal network configuration by solving the conflict among the at least two network automation functions.

8. The method according to claim 7 , wherein each configuration set comprises a range for a parameter having a minimum value and a maximum value, the parameter being the same for the configuration sets of the at least two network automation functions, and the method further comprises:

determining that a conflict is present by determining that the minimum values and the maximum values of ranges for the parameter of the configuration sets of the at least two network automation functions do not match with each other.

9. The method according to claim 6 , further comprising:

determining the optimal network configuration also based on a plurality of utility functions applied by the at least two network automation functions.

10. The method according to claim 6 , further comprising:

receiving a request from at least one network automation function to re-determine the optimal network configuration, the request comprising a modified configuration set, and

sending, in response to receiving the modified configuration set, a request to at least one other network automation function to provide configuration sets.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 7, 2022
From: BANERJEE, ANUBHAB; MWANJE, STEPHEN S.
To: NOKIA TECHNOLOGIES OY
Reel/Frame 061346/0078 →
Continuity (1)
Related Publication 20230188417A1 · Jun 15, 2023
References Cited (17)
US 20160127985A1 · Kayargadde · 2016 [cited by examiner]
US 20190273662A1 · Mwanje · 2019 [cited by examiner]
US 20210012183A1 · Elsken · 2021 [cited by examiner]
US 20230171158A1 · Mwanje · 2023 [cited by examiner]
WO 2012072445A1 · 2012 [cited by applicant]
WO 2018233818A1 · 2018 [cited by applicant]
Sarika et al., “Agenttab: An agent based approach to detect tabnabbing attack”, Procedia Computer Science, vol. 46, 2015, pp. 574-581. [cited by applicant]
Khayyat et al., “An intelligent multi-agent based model for collaborative logistics systems”, Transportation Research Procedia, vol. 12, 2016, pp. 325-338. [cited by applicant]
Rahimzadeh et al., “High reliable and efficient task allocation in networked multi-agent systems”, Autonomous Agents and Multi-Agent Systems, vol. 29, 2015, pp. 1023-1040. [cited by applicant]
Gupta et al., “Cooperative multi-agent control using deep reinforcement learning”, Autonomous Agents and Multiagent Systems, Nov. 25, 2017, pp. 66-83. [cited by applicant]
Liu et al., “A novel approach to task assignment in a cooperative multi-agent design system”, Applied Intelligence, vol. 43, Jan. 18, 2015, pp. 162-175. [cited by applicant]
Bianchi et al., “Heuristically-Accelerated Multiagent Reinforcement Learning”, IEEE Transactions on Cybernetics, vol. 44, No. 2, Feb. 2014, pp. 252-265. [cited by applicant]
Morstyn et al., “Cooperative Multi-Agent Control of Heterogeneous Storage Devices Distributed in a DC Microgrid”, IEEE Transactions on Power Systems, vol. 31, No. 4, Jul. 2016, pp. 2974-2986. [cited by applicant]
Nash, “The Bargaining Problem”, Econometrica, vol. 18, No. 2, Apr. 1950, pp. 155-162. [cited by applicant]
International Search Report and Written Opinion received for corresponding Patent Cooperation Treaty Application No. PCT/EP2020/061183, dated Dec. 16, 2020, 14 pages. [cited by applicant]
Mwanje et al., “Concurrent cooperative games for coordinating SON functions in cognitive cellular networks”, IEEE International Symposium on Integrated Network Management (IM), May 11-15, 2015, pp. 1298-1303. [cited by applicant]
Banerjee et al., “Game theoretic Conflict Resolution Mechanism for Cognitive Autonomous Networks”, International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS), Jul. 20-22, 2020, … [cited by applicant]